© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2053
    Prev
    Next
    INDEX
    Explanations

    linux usb drivers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfer
    -0.90
     TRANSFER
    -0.89
    Transfers
    -0.87
     Transfer
    -0.85
    TRANSFER
    -0.84
     Transfers
    -0.84
    transfer
    -0.81
     Erzb
    -0.78
     transfers
    -0.77
    綬
    -0.75
    POSITIVE LOGITS
     composites
    0.75
     באמצעות
    0.74
     Haddad
    0.73
    짤
    0.73
    optimize
    0.71
     engagements
    0.71
    Aug
    0.69
     port
    0.68
    lig
    0.68
    CIÓN
    0.68
    Activations Density 0.075%

    No Known Activations